Stars
ncnn android piper the fast and local neural text-to-speech engine
The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
Code for the paper "Jukebox: A Generative Model for Music"
PyTorch implementation of "FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."
High-quality speech synthesis with LoRA fine-tuning on index-tts, enhancing prosody and naturalness for single and multi-speaker voices.
Noise supression using deep filtering
Added vLLM support to IndexTTS for faster inference.
Text-audio foundation model from Boson AI
Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
[NeurIPS'24 Spotlight] Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text Prompts
[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。
🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT！🌏 Train a 64M-parameter GPT from scratch in just 2h!
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice
[ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"